An AI-based digital factory intelligent control method and system

Abstract

The present invention relates to the field of artificial intelligence control technology, and specifically discloses an AI-based digital factory intelligent control method and system. The data acquisition module monitors the performance of equipment in the production process in real time, distinguishes between qualified and unqualified product signals through statistical analysis of the qualified rate, and then identifies equipment performance abnormalities; the equipment performance analysis module deeply explores the root cause of equipment abnormalities, and the system also analyzes the correlation between temperature and voltage abnormalities to determine the main influencing factors, so as to accurately locate the equipment failure point; the intelligent allocation module classifies the equipment into first-level performance equipment and second-level performance equipment based on the analysis results of equipment performance, and intelligently allocates production tasks according to the equipment level; key or high-value components are preferentially allocated to equipment with more stable performance to ensure product quality; non-key components can be processed by second-level equipment to achieve optimal resource allocation.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence control technology, and in particular to an AI-based digital factory intelligent control method and system. Background Art

[0002] With the development of Industry 4.0, the concept of digital factory has gradually gained popularity. Traditional factory control systems rely on pre-programmed logic controllers (PLC) and manual intervention, which are difficult to adapt to the rapidly changing market demand and complex production environment. In modern manufacturing, it uses advanced information technology and automation technology to achieve digital and intelligent management of the production process. The key to this transformation is to achieve real-time monitoring and optimization of the production process by integrating various sensors, actuators and information systems.

[0003] The existing technology lacks the ability to quickly identify abnormal signals and then analyze the causes of abnormal equipment status. When abnormal equipment appears, there is a lack of intelligent allocation for different equipment performances during production and processing. The rational use of different equipment performances for production and processing has become a problem that needs to be solved urgently. Summary of the invention

[0004] The purpose of the present invention is to provide a digital factory intelligent control method and system based on AI.

[0005] By monitoring the equipment's qualification rate in real time, the system can quickly identify abnormal signals and analyze the reasons for abnormal equipment status. By dividing equipment into different performance levels and allocating production tasks accordingly, key or high-value components are preferentially allocated to equipment with better performance, thus ensuring high product quality and consistency. At the same time, the secondary equipment is reasonably used to handle non-critical tasks, achieving effective resource allocation and risk dispersion, and reducing the risk of production interruption.

[0006] To solve the above-mentioned background problems.

[0007] The purpose of the present invention can be achieved by the following technical solution: A digital factory intelligent control method and system based on AI, comprising the following steps:

[0008] Get the processing equipment i of the parts, i≥1, and evenly distribute the same parts to each equipment for production. Through the qualified rate analysis, generate product qualified signal and product unqualified signal;

[0009] Based on the product failure signal, analyze the temperature and voltage that affect the equipment status, obtain the temperature and voltage impact data, and determine the influencing factors of the equipment status based on the temperature and voltage impact data for analysis;

[0010] Among them, the temperature and pressure impact data include temperature anomaly ratio, voltage anomaly ratio and temperature and pressure anomaly ratio;

[0011] Process the impact of equipment abnormalities based on the influencing factors of equipment status, divide the equipment according to the qualified rate of parts and components, and complete the dynamic processing allocation of parts and components;

[0012] Among them, the equipment is divided into first-level performance equipment and second-level performance equipment.

[0013] As a further solution of the present invention: the same kind of parts are evenly distributed to each device for production;

[0014] By collecting the number of qualified parts ia and the number of unqualified parts ib of each device in the production cycle in real time, the qualified rate Pi of parts produced by each device is calculated; the qualified rate Pi of parts is compared with the preset minimum qualified rate requirement Pmin of parts;

[0015] If the component qualification rate Pi ≥ the preset minimum component qualification rate requirement Pmin, the component qualification rate is normal and a product qualification signal is generated;

[0016] If the component qualification rate Pi is less than the preset minimum component qualification rate requirement Pmin, the component qualification rate is abnormal and a product failure signal is generated.

[0017] As a further solution of the present invention: based on the product failure signal, the equipment performance is evaluated;

[0018] Collect the temperature and voltage values ​​during the equipment use cycle and analyze them to obtain temperature and voltage abnormality data: Analyze the voltage abnormality data to determine the impact of temperature abnormality or voltage abnormality on the equipment status;

[0019] The temperature and pressure anomaly data include the temperature anomaly ratio ATi, the voltage anomaly ratio BVj and the temperature and pressure anomaly time period ABk.

[0020] As a further solution of the present invention: the process of obtaining the temperature anomaly ratio ATi:

[0021] Divide the use cycle of each production equipment into several time sub-units, obtain the temperature value corresponding to the middle moment of each time sub-unit, and record it as the unit temperature value;

[0022] Compare the unit temperature value with the preset unit temperature range value to obtain a temperature anomaly signal;

[0023] Based on the temperature anomaly signal, the abnormal temperature deviation value of the time sub-unit is obtained, and the abnormal temperature deviation value is calculated by ratio with the closest unit temperature range value to obtain the temperature anomaly ratio ATi; the voltage anomaly ratio BVj acquisition process:

[0024] Compare the voltage value corresponding to the middle moment of each time sub-unit with the preset unit voltage range value to obtain a voltage abnormality signal;

[0025] Based on the voltage abnormality signal, the abnormal voltage deviation value of the time sub-unit is obtained, and the abnormal voltage deviation value is ratio-calculated with the closest unit voltage range value to obtain the voltage abnormality ratio BVj.

[0026] As a further solution of the present invention: the process of obtaining the abnormal temperature and pressure time period ABk is as follows:

[0027] Obtaining a time subunit corresponding to the temperature abnormality signal, and recording the time period corresponding to the time subunit as the temperature abnormality time period;

[0028] Acquire a time subunit corresponding to the voltage abnormality signal, and record the time period corresponding to the time subunit as the voltage abnormality time period;

[0029] The temperature abnormality time period and the voltage abnormality time period are overlapped, and the overlapping time period is recorded as the temperature and voltage abnormality time period.

[0030] As a further solution of the present invention: the temperature and pressure abnormality data analysis process is:

[0031] If the number of temperature abnormality time subunits is greater than the number of voltage abnormality time subunits, it means that the temperature abnormality has a greater impact on the status of the device;

[0032] If the number of temperature abnormality time subunits is less than the number of voltage abnormality time subunits, it means that the voltage abnormality has a greater impact on the status of the device;

[0033] If the number of temperature anomaly time subunits is equal to the number of voltage anomaly time subunits and both are greater than the number of time subunits corresponding to the temperature and voltage anomaly time period, it means that the voltage anomaly and the temperature anomaly have the same degree of influence on the device status;

[0034] If the number of temperature abnormality time subunits, the number of voltage abnormality time subunits and the number of time subunits corresponding to the temperature and pressure abnormality time period are equal, it means that the temperature abnormality or voltage abnormality interferes with each other, resulting in a decline in the equipment status.

[0035] As a further solution of the present invention: comparing the temperature anomaly ratio and the voltage anomaly ratio corresponding to the temperature and pressure anomaly time period,

[0036] Construct a plane coordinate system, with the x-axis representing the temperature and pressure anomaly time, and the y-axis representing the temperature anomaly ratio or the voltage anomaly ratio;

[0037] According to the time sequence of temperature and pressure anomalies, the temperature and pressure anomaly ratios are marked in the plane coordinate system to construct the temperature anomaly curve;

[0038] According to the time sequence of temperature and pressure anomalies, the voltage anomaly ratio is marked in the plane coordinate system to construct the voltage anomaly curve;

[0039] If both the temperature anomaly curve and the voltage anomaly curve show an increasing trend, the greater the temperature anomaly, the greater the voltage anomaly. There is a positive correlation between the voltage and temperature in the corresponding time period, indicating that the voltage and temperature jointly affect the equipment status.

[0040] As a further solution of the present invention: the classification standard of first-level performance equipment and second-level performance equipment is:

[0041] The minimum production qualification rate standard and the 100% qualification rate are used as the comparison interval;

[0042] The middle value of the comparison interval is used as the standard for dividing equipment performance;

[0043] Equipment with a production qualification rate greater than or equal to the median value is recorded as first-level performance equipment;

[0044] Equipment with a production pass rate less than the median value and greater than or equal to the minimum production standard is recorded as level-performance equipment.

[0045] As a further solution of the present invention: obtaining m first-level performance devices and n second-level performance devices;

[0046] Obtain the first-level performance equipment qualification rate Pm and the second-level performance equipment qualification rate Pn;

[0047] Let Xsm represent the number of s parts allocated to the mth first-level performance equipment;

[0048] Let Yqn represent the number of q parts allocated to the nth secondary performance device;

[0049] If z parts need to be processed and the output of z parts is maximized, ;

[0050] Among them, s=1, 2,..., s; q=1, 2,..., q; m=1, 2,..., m; n=1, 2,..., n; z=1, 2,..., z;

[0051] By formula Calculate the maximum output of qualified parts ; Find the solution that maximizes the output of qualified parts , the corresponding Xsm and Yqn are allocated.

[0052] As a further solution of the present invention: an AI-based digital factory intelligent control system, including: a data acquisition module, an equipment performance analysis module, and an intelligent allocation module:

[0053] A data acquisition module, wherein the data acquisition module obtains the processing equipment i of the parts, i≥1, distributes the same parts to each equipment for production, and generates a product qualified signal and a product unqualified signal through qualified rate analysis;

[0054] Equipment performance analysis module, which determines whether the abnormal product qualification rate is caused by abnormal equipment performance, analyzes the temperature and voltage that affect the equipment performance, obtains the temperature abnormality ratio, voltage abnormality ratio, temperature and pressure abnormality ratio, and determines the factors that have a greater impact on the equipment performance;

[0055] An intelligent allocation module divides the equipment in the factory into first-level performance equipment and second-level performance equipment according to the qualification rate of the products produced, and intelligently allocates the first-level performance equipment and the second-level performance equipment for parts processing.

[0056] Beneficial effects of the present invention:

[0057] (1) Implementing AI-based digital factory intelligent control systems can significantly improve production efficiency and product quality; by real-time monitoring of the equipment's qualification rate, the system can quickly identify abnormal signals and analyze the causes of abnormal equipment status, such as temperature and voltage fluctuations. This enables the factory to take corrective measures in a timely manner, such as adjusting the temperature or voltage of the working environment, or even maintaining or replacing the equipment, to prevent production stagnation and product quality degradation due to equipment failure. By dividing equipment into different performance levels and assigning production tasks accordingly, critical or high-value components are given priority to equipment with better performance, thereby ensuring high product quality and consistency. At the same time, the rational use of secondary equipment to handle non-critical tasks achieves effective resource allocation and risk diversification, reducing the risk of production interruptions;

[0058] (2) Through data analysis, the intelligent control system can accurately determine which equipment is in optimal working condition and which equipment needs maintenance or upgrading. This helps to optimize resource allocation and avoid production bottlenecks caused by over-reliance on a single device. The system can dynamically adjust the production plan based on the actual performance of the equipment, using primary equipment to increase production before peak demand periods and using secondary equipment to keep the production line running on weekdays. In addition, by regularly evaluating equipment performance and adjusting equipment levels and material allocation strategies in a timely manner, the factory can better respond to changes in market demand, reduce waste, and control costs. In the long run, this intelligent management can also reduce sudden failures and extend equipment life through preventive maintenance, thereby saving expenses on repair and replacement of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The present invention will be further described below in conjunction with the accompanying drawings.

[0060] Figure 1 It is a structural schematic diagram of an AI-based digital factory intelligent control method of the present invention;

[0061] Figure 2 This is a schematic diagram of an AI-based digital factory intelligent control method and a standard structure for judging the qualified rate of system components in the present invention;

[0062] Figure 3 This is a schematic diagram of the structure of an AI-based digital factory intelligent control system in the present invention; DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Example 1

[0065] See also Figure 1-Figure 2 As shown, the present invention is an AI-based digital factory intelligent control method and system, and the specific implementation steps are:

[0066] Get the processing equipment i of the parts, i≥1, and evenly distribute the same parts to each equipment for production. Through the qualified rate analysis, generate product qualified signal and product unqualified signal;

[0067] Based on the product failure signal, analyze the temperature and voltage that affect the equipment status, obtain the temperature and voltage impact data, and determine the influencing factors of the equipment status based on the temperature and voltage impact data for analysis;

[0068] Among them, the temperature and pressure impact data include temperature anomaly ratio, voltage anomaly ratio and temperature and pressure anomaly ratio;

[0069] Process the impact of equipment abnormalities based on the influencing factors of equipment status, divide the equipment according to the qualified rate of parts and components, and complete the dynamic processing allocation of parts and components;

[0070] Among them, the equipment is divided into first-level performance equipment and second-level performance equipment.

[0071] Example 2

[0072] Based on Example 1,

[0073] Take automobile parts processing equipment as an example:

[0074] Get the processing equipment i of the parts, i≥1, and evenly distribute the same parts to each equipment for production;

[0075] Real-time collection of the number of qualified parts ia and the number of unqualified parts ib for each device during the production cycle;

[0076] By formula Calculate the qualified rate Pi of components corresponding to each device;

[0077] Compare the parts qualification rate Pi with the minimum parts qualification rate requirement Pmin;

[0078] Among them, each component has a minimum pass rate requirement in factory production, which is usually set by the staff's experience;

[0079] If the component qualification rate Pi ≥ the preset minimum component qualification rate requirement Pmin, the component qualification rate is normal and a product qualification signal is generated;

[0080] If the component qualification rate Pi is less than the preset minimum component qualification rate requirement Pmin, the component qualification rate is abnormal and a product failure signal is generated;

[0081] Example 3

[0082] Based on Example 2,

[0083] Based on the component failure signal, determine whether the abnormal component qualification rate is caused by abnormal equipment status.

[0084] Failures in equipment status can lead to reduced production efficiency, which in turn reduces production levels;

[0085] Evaluate the status of the equipment:

[0086] The use cycle of each production equipment is divided into several time sub-units, the temperature data of each time sub-unit is collected by a temperature sensor, and the temperature value corresponding to the middle moment of each time sub-unit is recorded as the unit temperature value;

[0087] comparing the cell temperature value with a preset temperature threshold;

[0088] If the unit temperature is within the preset unit temperature range, a normal temperature signal is generated;

[0089] If the unit temperature is not within the preset unit temperature range, a temperature abnormality signal is generated;

[0090] When a temperature anomaly signal is obtained, the unit temperature is subtracted from the closest unit temperature range value, and the absolute value is taken to obtain the abnormal temperature deviation value, and then the abnormal temperature deviation value is divided by the closest unit temperature range value to obtain the temperature anomaly ratio ATi; the temperature anomaly ratios are arranged from large to small according to the numerical value to obtain the temperature anomaly ratio set {AT1, AT2, ..., ATj}

[0091] Where, i represents the i-th temperature abnormal time subunit, i=1, 2, ..., n;

[0092] The voltage data of each time sub-unit is collected by a voltage sensor, and the voltage value corresponding to the middle moment of each time sub-unit is recorded as the unit voltage value;

[0093] comparing the cell voltage value with a preset voltage threshold;

[0094] If the cell temperature is within the preset cell voltage range, a voltage normal signal is generated;

[0095] If the cell temperature is not within the preset cell voltage range, a voltage abnormality signal is generated;

[0096] When a voltage abnormality signal is obtained, the unit voltage is subtracted from the closest unit voltage range value, and the absolute value is taken to obtain the abnormal voltage deviation value, and then the abnormal voltage deviation value is divided by the closest unit voltage range value to obtain the voltage abnormality ratio BVj;

[0097] Where, j represents j voltage abnormal time subunit, j=1, 2, ..., n;

[0098] Arrange the voltage anomaly ratios from large to small according to their values ​​to obtain the voltage anomaly ratio set {BV1, BV2, ..., BVj}

[0099] The voltage anomaly ratio and the temperature anomaly ratio in the same time period are recorded as the temperature and pressure anomaly time period set {AB1, AB2, ..., ABk}, where k represents k temperature and pressure anomaly time periods, and the temperature and pressure anomaly time period is recorded as ABk;

[0100] It should be noted that abnormal temperature and abnormal voltage may cause equipment performance degradation, thus leading to equipment failure. The abnormal temperature and voltage time period here means that during this time period, both temperature and voltage are abnormal, thus leading to equipment failure. It can be judged that there may be an influence relationship between voltage and temperature.

[0101] Determine the factors that have a greater impact on the status of the equipment;

[0102] If i > j, it indicates that the number of temperature anomaly ratios is relatively large, which means that temperature anomalies have a greater impact on the state of the device; the device may be more sensitive to temperature changes, and even slight temperature fluctuations may cause the device state to be unstable; in contrast, voltage anomalies have a relatively smaller impact on the device state because modern electronic devices usually have a certain voltage tolerance range;

[0103] If i < j, it indicates that the number of voltage anomaly ratios is relatively large, which means that voltage anomalies have a greater impact on the state of the device; the device may be more sensitive to voltage changes, and even slight voltage fluctuations may cause abnormal functions or performance degradation of the device; relatively speaking, temperature anomalies have a smaller impact on device performance because the device may be designed to operate normally within a certain temperature range;

[0104] If i = j > k, it indicates that both voltage anomalies and temperature anomalies jointly affect the device state. In this case, both temperature and voltage anomalies have a significant impact on the device performance, and they may separately or jointly cause the device performance to decline at different time periods; in this case, specific analysis and handling are required for each type of anomaly to ensure the stable operation of the device under various environmental conditions;

[0105] If i = j = k, in this case, whether it is temperature anomalies or voltage anomalies, they may separately or jointly cause the device state to be abnormal; it is necessary to comprehensively consider and manage these temperature anomalies and voltage anomalies;

[0106] Compare the temperature anomaly ratio corresponding to the temperature and voltage anomaly time period with the voltage anomaly ratio.

[0107] Construct a plane coordinate system, with the x-axis as the temperature and voltage anomaly time and the y-axis as the temperature anomaly ratio or voltage anomaly ratio;

[0108] Mark the temperature anomaly ratio in the plane coordinate system according to the order of temperature and voltage anomaly time to construct a temperature anomaly curve;

[0109] Mark the voltage anomaly ratio in the plane coordinate system according to the order of temperature and voltage anomaly time to construct a voltage anomaly curve;

[0110] If both the temperature anomaly curve and the voltage anomaly curve show an increasing trend, the greater the degree of temperature anomaly, the greater the degree of voltage anomaly. There is a positive correlation between voltage and temperature during the corresponding time period, indicating that voltage and temperature jointly affect the device state.

[0111] It should be noted that: if there is no problem with product quality and there are no obvious abnormalities, then it can be further confirmed that the degradation of equipment performance is the direct cause of the abnormal product failure rate; once the degradation of equipment performance is determined to be the main cause, corrective measures should be immediately formulated, such as repairing or replacing the faulty equipment, and at the same time strengthening the daily maintenance and regular inspection of the equipment to avoid similar problems from happening again.

[0112] Example 4

[0113] On the basis of embodiments 2 and 3, the influence of equipment abnormality is processed based on the influencing factors of equipment status, and the equipment is divided into first-level performance equipment and second-level performance equipment according to the qualified rate of parts;

[0114] Among them, the classification standards for first-level performance equipment and second-level performance equipment are:

[0115] The minimum production qualification rate standard and the 100% qualification rate are used as the comparison interval;

[0116] The middle value of the comparison interval is used as the standard for dividing equipment performance;

[0117] Equipment with a production qualification rate greater than or equal to the median value is recorded as first-level performance equipment;

[0118] Equipment with a production pass rate less than the median value and greater than or equal to the minimum production standard is recorded as first-level performance equipment;

[0119] If the production qualification rate is less than the middle qualification rate of the production qualification rate comparison interval and greater than the minimum standard of production qualification rate, it is a Class II performance equipment;

[0120] Allocate parts processing for first-level performance equipment and second-level performance equipment:

[0121] Obtain m first-level performance devices and n second-level performance devices;

[0122] Obtain the first-level performance equipment qualification rate Pm and the second-level performance equipment qualification rate Pn;

[0123] Let Xsm represent the number of s parts allocated to the mth first-level performance equipment;

[0124] Let Yqn represent the number of q parts allocated to the nth secondary performance device;

[0125] If z parts need to be processed and the output of z parts is maximized, ;

[0126] Among them, s=1, 2,..., s; q=1, 2,..., q; m=1, 2,..., m; n=1, 2,..., n; z=1, 2,..., z;

[0127] By formula Calculate the maximum output of qualified parts ; Find the solution that maximizes the output of qualified parts , the corresponding Xsm and Yqn are allocated.

[0128] It should be noted that the division between first-level performance equipment and second-level performance equipment should be based on the stability and production efficiency of the equipment; first-level performance equipment refers to those equipment with better performance, higher stability and faster production efficiency; while second-level performance equipment may have slower production speeds or lower stability under specific conditions.

[0129] Real-time Example 5

[0130] See also Figure 3 As shown, an AI-based digital factory intelligent control system includes: data acquisition module, equipment performance analysis module, and intelligent allocation module:

[0131] A data acquisition module, wherein the data acquisition module obtains the processing equipment i of the parts, i≥1, distributes the same parts to each equipment for production, and generates a product qualified signal and a product unqualified signal through qualified rate analysis;

[0132] Equipment performance analysis module, which determines whether the abnormal product qualification rate is caused by abnormal equipment performance, analyzes the temperature and voltage that affect the equipment performance, obtains the temperature abnormality ratio, voltage abnormality ratio, temperature and pressure abnormality ratio, and determines the factors that have a greater impact on the equipment performance;

[0133] An intelligent allocation module divides the equipment in the factory into first-level performance equipment and second-level performance equipment according to the qualification rate of the products produced, and intelligently allocates the first-level performance equipment and the second-level performance equipment for parts processing.

[0134] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An AI-based digital factory intelligent control method, characterized in that: The following steps are involved: Multiple parts in the same process are evenly distributed to multiple devices for production. The number of devices is recorded as i, i>1. Through the qualified rate analysis, the qualified product signal and the unqualified product signal are generated; Based on the product failure signal, analyze the temperature and voltage that affect the equipment status, obtain temperature and pressure impact data, and analyze the factors affecting the equipment status based on the temperature and pressure impact data; Among them, the temperature and pressure impact data include temperature anomaly ratio, voltage anomaly ratio and temperature and pressure anomaly ratio; Handle equipment anomalies based on factors affecting equipment status, divide equipment into groups according to the qualified rates of parts, and complete dynamic processing allocation of parts; Among them, the equipment is divided into first-level performance equipment and second-level performance equipment.

2. The AI-based digital factory intelligent control method according to claim 1, characterized in that: The process of identifying the production status of the equipment is as follows: Collect the number of qualified parts ia and unqualified parts ib of each device in the production cycle in real time, and calculate the qualified rate Pi of parts produced by each device; Compare the parts qualification rate Pi with the preset minimum parts qualification rate requirement Pmin; If the component qualification rate Pi ≥ the preset minimum component qualification rate requirement Pmin, the component qualification rate is normal and a product qualification signal is generated; If the component qualification rate Pi is less than the preset minimum component qualification rate requirement Pmin, the component qualification rate is abnormal and a product failure signal is generated.

3. The AI-based digital factory intelligent control method according to claim 2 is characterized in that: Evaluate equipment performance based on product failure signals; During the usage cycle, the temperature and voltage values ​​of the equipment are collected and analyzed to obtain temperature and voltage anomaly data: Determine the degree of impact of temperature or voltage anomalies on equipment status based on temperature and voltage anomaly data; The temperature and pressure anomaly data include the temperature anomaly ratio ATi, the voltage anomaly ratio BVj and the temperature and pressure anomaly time period ABk.

4. The AI-based digital factory intelligent control method according to claim 3 is characterized in that: The process of obtaining the temperature anomaly ratio ATi: Divide the use cycle of each production equipment into several time sub-units, obtain the temperature value corresponding to the middle moment of each time sub-unit, and record it as the unit temperature value; Compare the unit temperature value with the preset unit temperature range value to obtain a temperature anomaly signal; Based on the temperature anomaly signal, the abnormal temperature deviation value of the time sub-unit is obtained, and the abnormal temperature deviation value is calculated by ratio with the closest unit temperature range value to obtain the temperature anomaly ratio ATi; The process of obtaining the voltage anomaly ratio BVj is as follows: Obtain the voltage value corresponding to the middle moment of each time sub-unit, and record it as the unit voltage value; Compare the unit voltage value with a preset unit voltage range value to obtain a voltage anomaly signal; Based on the voltage anomaly signal, the abnormal voltage deviation value of the time sub-unit is obtained, and the ratio of the abnormal voltage deviation value to the closest unit voltage range value is calculated to obtain the voltage anomaly ratio BVj.

5. The AI-based digital factory intelligent control method according to claim 4 is characterized in that: The process of obtaining the abnormal temperature and pressure time period ABk is as follows: Obtaining a time subunit corresponding to the temperature anomaly signal, and recording the time period corresponding to the time subunit as the temperature anomaly time period; Obtaining a time subunit corresponding to the voltage abnormality signal, and recording the time period corresponding to the time subunit as the voltage abnormality time period; The temperature abnormality time period and the voltage abnormality time period are overlapped, and the overlapping time period is recorded as the temperature and voltage abnormality time period.

6. The AI-based digital factory intelligent control method according to claim 5 is characterized in that: The analysis process of temperature and pressure anomaly data is as follows: If the number of temperature anomaly time subunits is greater than the number of voltage anomaly time subunits, it means that the temperature anomaly has a greater impact on the device status; If the number of temperature anomaly time subunits is smaller than the number of voltage anomaly time subunits, it means that the voltage anomaly has a greater impact on the device status; If the number of temperature anomaly time subunits is equal to the number of voltage anomaly time subunits and both are greater than the number of time subunits corresponding to the temperature and voltage anomaly time period, it means that the voltage anomaly and the temperature anomaly have the same impact on the device status; If the number of temperature anomaly time subunits, the number of voltage anomaly time subunits, and the number of time subunits corresponding to the temperature and pressure anomaly time period are equal, it means that the temperature anomaly or the voltage anomaly interferes with each other.

7. The AI-based digital factory intelligent control method according to claim 5, characterized in that: Compare the temperature anomaly ratio and voltage anomaly ratio corresponding to the temperature and pressure anomaly period. Construct a plane coordinate system with the x-axis representing the temperature and pressure anomaly time and the y-axis representing the temperature anomaly ratio or voltage anomaly ratio; According to the time sequence of temperature and pressure anomalies, the temperature and pressure anomaly ratios are marked in the plane coordinate system to construct the temperature anomaly curve; According to the time sequence of temperature and pressure anomalies, the voltage anomaly ratio is marked in the plane coordinate system to construct the voltage anomaly curve; If both the temperature anomaly curve and the voltage anomaly curve show an increasing trend, the greater the temperature anomaly, the greater the voltage anomaly. There is a positive correlation between the voltage and temperature in the corresponding time period, indicating that the voltage and temperature jointly affect the equipment status.

8. The AI-based digital factory intelligent control method according to claim 7 is characterized in that: The classification standards for first-level performance equipment and second-level performance equipment are: Use the minimum production qualification rate standard and the 100% qualification rate as the comparison range; The middle value of the comparison interval is used as the standard for dividing equipment performance; Equipment with a production qualification rate greater than or equal to the median value is recorded as first-level performance equipment; Equipment with a production qualification rate less than the median value and greater than or equal to the minimum production standard is recorded as secondary performance equipment.

9. The AI-based digital factory intelligent control method according to claim 8, characterized in that: Allocate parts processing between first-level performance equipment and second-level performance equipment; Obtain m first-level performance devices and n second-level performance devices; Obtain the first-level performance equipment qualification rate Pm and the second-level performance equipment qualification rate Pn; Let Xsm represent the number of s parts allocated to the mth first-level performance equipment; Let Yqn represent the number of q parts allocated to the nth secondary performance device; If z parts need to be processed and the output of z parts is maximized, ; Among them, s=1, 2,..., s; q=1, 2,..., q; m=1, 2,..., m; n=1, 2,..., n; z=1, 2,..., z; By formula Calculate the maximum output of qualified parts ; Find the solution that maximizes the output of qualified parts , the corresponding Xsm and Yqn are allocated.

10. An AI-based digital factory intelligent control system, comprising: Data acquisition module, equipment performance analysis module, intelligent allocation module: A data acquisition module, which obtains the processing equipment i of the parts, where i>1, distributes the same parts evenly to each equipment for production, and generates product qualified and product unqualified signals through qualified rate analysis; Equipment performance analysis module, which determines whether abnormal product qualification rate is caused by abnormal equipment performance, analyzes the temperature and voltage that affect equipment performance, obtains the temperature abnormality ratio, voltage abnormality ratio, and temperature-pressure abnormality ratio, and determines the factors that have the greatest impact on equipment performance; An intelligent allocation module divides the equipment in the factory into first-level performance equipment and second-level performance equipment according to the level of qualified products produced, and intelligently allocates the first-level performance equipment and second-level performance equipment for parts processing.

Images